agentleFS
szarkansszarkans/dont-forget/skills/health/SKILL.md

health

Skill6 starsChanged 45 days agoMITView on GitHub

Commit the vault and report its indexed health.

53 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use plan-tune, ios-clean and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • ShreyRaviSkill

    plan-tune

    Self-tuning question sensitivity + developer psychographic for gstack (v1: observational). Review which AskUserQuestion prompts fire across gstack skills, set per-question preferences (never-ask / always-ask / ask-only-for-one-way), inspect the dual-track profile (what you declared vs what your behavior suggests), and enable/disable question tuning. Conversational interface — no CLI syntax required.

    Also in 9 projects that use this

  • Saqlain-811Skill

    ios-clean

    Remove the DebugBridge SPM package and all #if DEBUG wiring from an iOS app. (gstack)

    Also in 5 projects that use this

  • Saqlain-811Skill

    ios-fix

    Autonomous iOS bug fixer. (gstack)

    Also in 5 projects that use this

  • seek888Skill

    pair-agent

    Pair a remote AI agent with your browser. One command generates a setup key and prints instructions the other agent can follow to connect. Works with OpenClaw, Hermes, Codex, Cursor, or any agent that can make HTTP requests. The remote agent gets its own tab with scoped access (read+write by default, admin on request). Use when asked to "pair agent", "connect agent", "share browser", "remote browser", "let another agent use my browser", or "give browser access". (gstack) Voice triggers (speech-to-text aliases): "pair agent", "connect agent", "share my browser", "remote browser access".

    Also in 11 projects that use this

  • ShreyRaviSkill

    landing-report

    Read-only queue dashboard for workspace-aware ship. Shows which VERSION slots are currently claimed by open PRs, which sibling Conductor workspaces have WIP work likely to ship soon, and what slot /ship would pick next. No mutations — just a snapshot. Use when asked to "landing report", "what's in the queue", "show me open PRs", or "which version do I claim next". (gstack)

    Also in 8 projects that use this

  • timurgaleevSkill

    document-generate

    Generate missing docs for a feature, module or project as tutorials, how-tos, reference and explanation.

    Also in 7 projects that use this

  • +1 more from Saqlain-811
  • +2 more from ShreyRavi

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 38 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Create a local Git snapshot, then explain the health report from the disposable index.

    line 9
  2. Distinctive:

    Keep the report concise. Mention when displayed lists are capped and distinguish their displayed length from their full count.

    line 22

“Common” is measured: kept by at least 6 in 10 of the 38 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Check Vault Health

Create a local Git snapshot, then explain the health report from the disposable index. The vault stays read-only apart from Git metadata and the commit.

  • Compare the index timestamp at ~/.dont-forget/index.db with the newest vault note modification. If the index is missing or older, run python3 "${CLAUDE_PLUGIN_ROOT}/scripts/index.py" before producing the report.
  • Run python3 "${CLAUDE_PLUGIN_ROOT}/scripts/index.py" --embed to fill missing or malformed semantic vectors. Report its embedding.semantic field and any embedding.old_vector_files; if it is off, keep the rest of the health report useful. Each index owns <index filename>.vectors-<model>-<revision>.db, which survives rebuilds. The cached model runs offline; the first full pass can take about an hour on this CPU.
  • Check whether the vault root is a Git repository. If it is not, run git init there, create .gitignore containing .obsidian/workspace*.json, stage everything, and make the first commit.
  • If the repository already exists, stage the notes this session wrote by name — git add -- "<path>" "<path>" — and commit them with checkup: YYYY-MM-DD. For another commit on the same day, append #2, then increment that suffix as needed. When this session wrote nothing, commit nothing and go straight to the report. Naming paths is what replaces git add -A: one vault is shared by parallel sessions, and staging everything commits a neighbour's half-written notes under this session's message. Do not push; pushing is the user's decision.
  • Run git status --porcelain -- "*.md" in the vault and report the count as N uncommitted notes, naming the files while the list is short. Committing named paths means a session that dies mid-close leaves its notes outside Git indefinitely — nothing sweeps them up later — so this line is the only thing that surfaces them.
  • Run python3 "${CLAUDE_PLUGIN_ROOT}/scripts/checkup.py" and explain the result plainly: total notes, islands, unresolved-link candidates, and stale notes.
  • An island is a group of notes cut off from the main graph body. Report each with its size: a size-1 island is a lone orphan note; a size-2+ island is a cluster that links only to itself (name its members). These are candidates to bridge into the graph, not errors to fix automatically.
  • Treat unresolved links as candidates, because they may refer to attachments or headings. Show the list and offer to investigate; do not repair links automatically.
  • Treat stale notes as a report only. Do not edit or delete them unless the user explicitly asks to update them.
  • If Git is unavailable or the commit fails, say so honestly and still show the health report.

Keep the report concise. Mention when displayed lists are capped and distinguish their displayed length from their full count.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.